Skip to main content

Privacy Protection (PII)

The Privacy Protection tile lets AI-Public automatically check chat messages for personally identifiable information (PII) before they are sent to the AI. Per category, you configure how the system handles detected data.

What is PII protection?

PII stands for Personally Identifiable Information – data that can directly or indirectly identify a person, such as email addresses, social security numbers, credit card data or phone numbers.

When PII protection is enabled, user chat messages are analysed before reaching the AI. Depending on the configured action per category, data is passed through, anonymised, masked or blocked.

Enabling PII protection

The Privacy Protection tile is located in the management environment.

  1. Go to the management environment
  2. Select the Privacy Protection tile
  3. Enable the Activate PII protection switch
  4. Configure the desired action per category
  5. Click Save

While the switch is disabled, chat messages are forwarded unchanged.

Available actions per category

ActionDescription
Pass throughThe information is forwarded unchanged. Use this for data that poses no risk.
AnonymiseThe information is fully replaced by a placeholder (e.g. jan@organisation.com[EMAIL]). The AI does not see the real data.
MaskThe information is partially hidden (e.g. ****-****-****-1234). The type is recognisable, but the full value is not.
BlockThe chat message is completely blocked and not sent to the AI. Use this for highly sensitive information.

Available categories

CategoryWhat is detected
Email addressesAddresses such as jan@example.com
Credit card numbersVisa, Mastercard and other cards
Social security numbers (BSN)9-digit BSN numbers
Phone numbersDutch and international formats
IBAN / Bank account numbersNational and international IBAN numbers
IP addressesIPv4 and IPv6 addresses
Passport / ID numbersPassport and identity card numbers
Medical informationMedical terms and health information
URLsWeb links and page addresses
MAC addressesMAC addresses of network devices

A common configuration for your environment:

CategoryRecommended action
Email addressesPass through
BSNMask
Credit card numbersMask
IBANMask
Phone numbersMask
Medical informationAnonymise
IP addressesMask
URLsPass through
Passport / ID numbersMask
MAC addressesMask

How does medical information detection work?

The Medical information category works differently from the other categories. Because medical data is much more varied in nature, AI-Public uses heuristic keyword-based detection.

The system scans chat messages for a fixed list of medical terms in both Dutch and English:

DutchEnglish
diagnose / diagnosesdiagnosis
medicijn / medicatiemedication
allergie / allergieënallergy / allergies
bloeddrukblood pressure
hartslagheart rate
cholesterolcholesterol
diabetesdiabetes
insulineinsulin
patiëntpatient
symptoom / symptomensymptom
behandeling
operatie

Limitations

  • False positives – a sentence such as "The operation of the company went smoothly" may be flagged as medical.
  • False negatives – a rare condition not in the list will not be detected.
Advice

Use the Anonymise setting for medical information (the default). The exact medical term is replaced by a placeholder, so the AI retains context without seeing the specific data. Use Mask if you only want to partially hide the term.

Read and write permissions

Administrators with read-only access can view the settings but not change them. Contact AI-Public if you want to make changes but do not have sufficient permissions.

See also